Misbehavior Detection for Position Falsification Attacks in VANETs Using Machine Learning

Abstract

Cooperative Intelligent Transport Systems (C-ITS) is an advanced technology for road safety and traffic efficiency over Vehicular Ad Hoc Networks (VANETs) allowing vehicles to communicate with other vehicles or infrastructures. The security of VANETs is one of the main concerns in C-ITS because there may be some attacks in such type of network that may endanger the safety of the passengers. Intrusion Detection Systems (IDS) play an important role to protect the vehicular network by detecting misbehaving vehicles. In general, the works in the literature use the same well-known features in a centralized IDS. In this paper, we propose a Machine Learning (ML) mechanism that takes advantage of three new features, which are mainly related to the sender position, allowing to enhance the performances of IDS for position falsification attacks. Besides, it presents a comparison of two different ML methods for classification, i.e. k-Nearest Neighbor (kNN) and Random Forest (RF) that are used to detect malicious vehicles using these features. Finally, Ensemble Learning (EL) which combines different ML methods, in our case kNN and RF, is also carried out to improve the detection performance. An IDS is constructed allowing vehicles to detect misbehavior in a distributed way, while the detection mechanism is trained centrally. The results demonstrate that the proposed mechanism gives better results, in terms of classification performance indicators and computational time, than the best previous approaches on average.INDEX TERMS misbehavior detection, machine learning, vehicular ad hoc network, intelligent transport systems, dataset.

A Fuzzy-Based Context-Aware Misbehavior Detecting Scheme for Detecting Rogue Nodes in Vehicular Ad Hoc Network

“…Moreover, the model relies on reputation and long-term trust establishment, which is complex and is not suitable for early detection and new misbehaving nodes. Authors in [ 37 ] investigated different machine learning techniques to design a misbehavior detection model. Then, an ensemble of two machine learning techniques, namely k-nearest neighbor (kNN) and random forest (RF) classifiers, were used to construct the detection classifier.…”

“…Therefore, there is no deterministic correlation between the quality of shared information and the malicious intent of the vehicles. Moreover, machine-learning-based techniques in [ 33 , 34 , 35 , 36 , 37 ] are scenario-specific and assume a stationary correlation between data accuracy and vehicle class, which is not always the case in the highly dynamic context. Accordingly, such an assumption leads to low detection accuracy.…”

RSU-Based Online Intrusion Detection and Mitigation for VANET

“…A cooperative misbehavior detection model is proposed in [ 30 ] for detecting emergency message and position falsification attacks. In [ 34 , 35 , 36 ], the authors studied supervised learning models for detecting false position attacks in VANET. A new research direction studies false data injection attacks using time-series ML models, such as LSTM or GRU [ 37 , 38 ].…”

Detecção incremental de comportamento malicioso em VANETs

“…Dentre as abordagens que fazem uso de aprendizado de máquina, os artigos [Ercan et al 2021, Ercan et al 2022] apresentam novas features e combinac ¸ão de features para ajudar na detecc ¸ão das mensagens falsificadas, extraindo novas informac ¸ões dos dados já disponíveis nas BSM, aperfeic ¸oando a detecc ¸ão de certos tipos de ataque, embora faltem dados sobre o treinamento e propagac ¸ão dos modelos. Outra abordagem, [Sharma and Jaekel 2022], faz uso da infraestrutura para obter o conjunto de mensagens e treiná-las.…”